CN110458840B - Method, system and terminal equipment for reducing panel defect over-detection rate - Google Patents
Method, system and terminal equipment for reducing panel defect over-detection rate Download PDFInfo
- Publication number
- CN110458840B CN110458840B CN201910965886.6A CN201910965886A CN110458840B CN 110458840 B CN110458840 B CN 110458840B CN 201910965886 A CN201910965886 A CN 201910965886A CN 110458840 B CN110458840 B CN 110458840B
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- camera
- panel
- filtered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method, a system and a terminal device for reducing the over-detection rate of panel defects, wherein the method comprises the following steps: acquiring a first image of a display picture of a panel to be detected shot by a first camera and a second image of the display picture shot by a second camera; the second camera is a color camera; extracting a first defect area to be filtered in the first image; transforming the second image to an HSV color space, extracting an S-channel image and extracting a second defect area to be filtered from the S-channel image; calculating the contact ratio of the first defect region and the second defect region, and filtering out the first defect region with the contact ratio larger than a preset contact ratio threshold value; according to the invention, the contact ratio between the two defect areas is used as an index, the first defect area is filtered through the second defect area, the sucker printing area is effectively screened out and filtered, the sucker printing is prevented from being mistakenly detected as a defect, and the over-detection rate is effectively reduced.
Description
Technical Field
The invention belongs to the technical field of automatic defect detection, and particularly relates to a method, a system and terminal equipment for reducing the over-detection rate of panel defects.
Background
In the field of LCD panel Inspection, panel defect Inspection is generally implemented by replacing manual Inspection with an Automated Optical Inspection (AOI) Inspection method, so as to improve production efficiency. AOI testing process contains pan feeding, detects and the three stage of ejection of compact, and under the normal condition, AOI detection cycle is short, can realize quick pan feeding, detection and the ejection of compact of panel. When unexpected abnormal conditions occur, the panel to be detected can be adsorbed on the sucking disc for a long time, so that sucking disc marks with different depths are formed on the panel. When this panel passes through AOI detection station, the sucking disc seal on the panel can't disappear fast, is detected as the defect to lead to the overdetection. Therefore, when defect detection is carried out on the AOI detection station, the sucker print defects need to be filtered out to avoid the over-detection condition.
Generally, the suction cup print defect has a large area on the image and has a circular shape. During AOI detection, the suction cup mark defects are filtered by detecting the area and the circularity of the defects through a first camera. However, when the suction pad print is relatively light, errors occur in the area and the circularity of the suction pad print defect detected by the first camera, so that the suction pad print is still detected as a defect, and the overdetection rate of the filtering method is still high. To solve this problem, it is necessary to provide an effective solution for filtering the suction cup print defects to reduce the over-inspection.
Disclosure of Invention
The invention provides a method, a system and a terminal device for reducing the excessive inspection rate of panel defects, aiming at solving the problem that the excessive inspection rate is high because the existing defect detection mode is easy to detect the insubstantial defects such as sucker marks.
To achieve the above object, according to a first aspect of the present invention, there is provided a method for reducing an over-detection rate of panel defects, comprising the steps of:
acquiring a first image of a display picture of a panel to be detected shot by a first camera and a second image of the display picture shot by a second camera; the second camera is a color camera;
extracting a first defect area to be filtered in the first image;
transforming the second image to an HSV color space, extracting an S-channel image and extracting a second defect area to be filtered from the S-channel image;
and calculating the coincidence degree of the first defect region and the second defect region, and filtering the first defect region with the coincidence degree larger than a preset coincidence degree threshold value.
Preferably, the method for reducing the panel defect overdetection rate further comprises:
calibrating the first image and the second image to obtain an image transformation ratio between the first image and the second image; scaling the second defective region according to the image transformation ratio to match the size of the first defective region.
Preferably, in the method for reducing the panel defect overdetection rate, the extracting the first defect region to be filtered in the first image specifically includes:
filtering and enhancing the first image;
and calculating a segmentation threshold according to the detection sensitivity of the first camera, and performing threshold segmentation and feature selection on the enhanced first image according to the segmentation threshold to obtain a first defect region to be filtered.
Preferably, in the method for reducing the panel defect overdetection rate, the extracting the second defect area to be filtered from the S-channel image specifically includes:
and calculating a segmentation threshold according to the detection sensitivity of the second camera, and performing threshold segmentation and feature selection on the S-channel image according to the segmentation threshold to obtain a second defect area to be filtered.
Preferably, before transforming the second image into the HSV color space, the method for reducing the panel defect overdetection rate further includes:
and self-enhancing the second image, and dividing the square of the gray value of each pixel point in the second image by the average gray value of the second image.
Preferably, before calibrating the first image and the second image, the method for reducing the panel defect overdetection rate further includes: distortion correction and perspective transformation are performed on the first image and the second image respectively.
Preferably, in the method for reducing the panel defect overdetection rate, the image transformation ratio includes a row scaling ratio and a column scaling ratio, and the second defect area is scaled according to the row scaling ratio and the column scaling ratio.
According to a second aspect of the present invention, there is also provided a system for reducing the panel defect overdetection rate, the system comprising:
the device comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring a first image of a display picture of a panel to be detected, which is shot by a first camera, and a second image of the display picture, which is shot by a second camera;
the defect detection unit is used for extracting a first defect area to be filtered in the first image; the second image is transformed to an HSV color space, an S channel image is extracted, and a second defect area to be filtered is extracted from the S channel image;
and the filtering unit is used for calculating the contact ratio of the first defect region and the second defect region and filtering the first defect region with the contact ratio larger than a preset contact ratio threshold value.
Preferably, the system for reducing the panel defect overdetection rate further comprises a calibration unit;
the calibration unit is used for calibrating the first image and the second image to obtain the image transformation ratio between the first image and the second image;
the filtering unit scales the second defect region to match the size of the first defect region according to the image transformation ratio.
Preferably, in the system for reducing the panel defect overdetection rate, the step of extracting, by the defect detection unit, the first defect area to be filtered in the first image specifically includes:
filtering and enhancing the first image;
and calculating a segmentation threshold according to the detection sensitivity of the first camera, and performing threshold segmentation and feature selection on the enhanced first image according to the segmentation threshold to obtain a first defect region to be filtered.
Preferably, in the system for reducing the panel defect overdetection rate, the step of extracting the second defect area to be filtered from the S-channel image by the defect detection unit specifically includes:
and calculating a segmentation threshold according to the detection sensitivity of the second camera, and performing threshold segmentation and feature selection on the S-channel image according to the segmentation threshold to obtain a second defect area to be filtered.
Preferably, in the system for reducing the panel defect overdetection rate, before the transforming the second image into the HSV color space, the defect detecting unit further includes:
and self-enhancing the second image, and dividing the square of the gray value of each pixel point in the second image by the average gray value of the second image.
Preferably, the system for reducing the panel defect overdetection rate further comprises a correction unit;
the correction unit is used for respectively carrying out distortion correction and perspective transformation on the first image and the second image.
Preferably, in the system for reducing the panel defect overdetection rate, the image transformation ratio includes a row scaling ratio and a column scaling ratio; and the filtering unit scales the second defect area according to the row scaling ratio and the column scaling ratio.
According to a third aspect of the present invention, there is also provided a terminal device, comprising at least one processing unit, and at least one memory unit,
wherein the storage unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform any of the steps of the method for reducing the panel defect overdetection rate.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
according to the method, the system and the terminal equipment for reducing the panel defect over-inspection rate, the defect area extracted from the second image shot by the second color camera is adopted to filter the defect area detected by the first camera, the coincidence degree between the two defect areas is used as a judgment index, the first defect area is filtered through the second defect area, the sucking disc printing area is effectively screened out and filtered, the sucking disc printing is prevented from being detected as the defect by mistake, and the over-inspection rate is effectively reduced.
Drawings
FIG. 1 is a flowchart illustrating a method for reducing an undetected rate of a panel defect according to an embodiment of the present invention;
FIG. 2 is a logic diagram of a system for reducing panel defect overdetection rate according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Various defects of different types such as foreign matters, bubbles, scratches, burrs, press bright spots and the like can appear in the production process of the LCD panel, directly influence the final quality of the LCD panel and the output result of the finished product grade, and need to be accurately detected in the defect detection process; however, in the detection process, sucker marks with different depths, which are generated by the fact that the LCD panel is adsorbed on the sucker for a long time, can disappear after a period of time, and the quality of the panel cannot be affected; if the suction pad print does not disappear when the AOI inspection is performed, it is highly likely to be detected as a defect, resulting in an over-inspection of the panel.
The method for reducing the panel defect overdetection rate provided by the embodiment can filter the defects such as sucker marks and the like which cannot influence the final quality of the panel, and avoid the overdetection condition; FIG. 1 is a flowchart illustrating a method for reducing an undetected rate of a panel defect according to an embodiment; as shown in fig. 1, the method comprises the steps of:
s1: the method comprises the steps that a first camera and a second camera are adopted to shoot the same display picture of a panel to be detected at the same time, wherein the display picture shot by the first camera is marked as a first image, and the display picture shot by the second camera is marked as a second image;
the method comprises the steps of firstly lighting a panel to be detected to enable the panel to be detected to display a picture, wherein the display picture is preferably a gray scale picture, generally a 63-order or 117-order gray scale picture, as a preferred embodiment, a first camera is a black and white camera, a second camera is a color camera, the color camera comprises color information, so that the defects of an image collected by the color camera are more obvious, and the defects of a suction cup print are further enhanced after color space conversion.
As a preferable mode of the present embodiment, after the first image and the second image are acquired, the first image and the second image are first subjected to image correction, and the image correction includes two steps of distortion correction and perspective transformation; in the practical application process, the images shot by the first camera and the second camera are likely to have inclination and distortion; the distortion correction mainly aims at eliminating the influence of radial distortion of a lens, and the distortion of the lens for AOI detection is smaller; the correction formula is as follows:
f(x,y)=F *Img(x,y)
wherein Img (x, y) is an uncorrected image, F is a correction mapping relation, and F (x, y) is a corrected image.
The main purpose of perspective transformation is to correct the acquired oblique image, and the transformation formula is as follows:
G(x,y)= HomMat2D*f(x,y)
where f (x, y) is the pre-transform image, HomMat2D is the transform matrix, and G (x, y) is the post-transform image.
As a preference of this embodiment, the method further includes, after the image correction of the first image and the second image:
s2: calibrating the first image and the second image to obtain an image transformation ratio between the first image and the second image;
if the relative positions of the first camera, the second camera and the panel to be detected are different when the display picture of the panel to be detected is shot, the angles and the sizes of the panel to be detected in the images acquired by the first camera, the second camera and the panel to be detected are different; the main purpose of image calibration is to calibrate the scaling ratio of the rows and columns of the first camera and the second camera, so as to prepare for subsequently transforming the sucker print defects in the first image acquired by the second camera into the second image acquired by the first camera; the specific calibration step comprises row calibration and column calibration, wherein the row calibration corresponds to a horizontal calibration line, and the column calibration corresponds to a vertical calibration line. The calibration formula is as follows:
Sacle(x)=LengthC1/ LengthC2
Sacle(y)=LengthR1/ LengthR2
wherein Sacle (x) is the line scaling ratio of the first and second cameras; lenthc 1 is the length of the horizontal calibration line in the first camera; lenthc 2 is the length of the horizontal calibration line in the second camera;
sacle (y) is the column scaling ratio of the first and second cameras; lenthr 1 is the length of the vertical calibration line in the first camera; lenthr 2 is the length of the vertical calibration line in the second camera.
Those skilled in the art will readily understand that the image calibration step described above may not be performed if the relative positions of the first camera, the second camera and the panel to be measured are the same.
S3: detecting the defects of the first image to obtain a first defect area to be filtered; detecting the defects of the second image to obtain a second defect area to be filtered;
the process of detecting the defects of the first image comprises three parts, namely image preprocessing, threshold segmentation and feature selection;
image preprocessing: firstly, performing median filtering on an original image RawImagbig (x, y) of a first image to obtain an image FilterImag (x, y), and certainly, filtering modes such as mean filtering and Gaussian filtering can also be adopted, which is not specifically limited in this embodiment;
and then, subtracting the original image RawImagbig (x, y) and the filtered image FilterImag (x, y) to obtain SubImag (x, y), and finally, carrying out image enhancement on the SubImag (x, y) to expand the gray scale range to 0-255 to obtain ScaleImage (x, y).
Threshold segmentation: firstly, setting the detection sensitivity of a first camera, wherein the range of the detection sensitivity is [0,1 ]; then, a segmentation threshold is calculated according to the detection sensitivity, and the relationship between the segmentation threshold and the sensitivity is calculated as follows:
ThresholdBig =（-SensitivityBig）* 128 + 255
wherein SensitivityBig is the detection sensitivity of the first camera, and threshold big is the segmentation threshold.
And finally, performing threshold segmentation on the scaleImage (x, y) according to the segmentation threshold ThresholdBig, and extracting a defective region RegionDefect.
Selecting characteristics: and screening a RegionDefect InBig (x, y) region possibly corresponding to the sucker print from the defect region RegionDefect according to the characteristics of the area, the circularity and the like of the sucker print.
So far, the suction mark defect detection of the first camera is completed.
The process of detecting the defects of the second image comprises three parts of image preprocessing, threshold segmentation and feature selection;
image preprocessing: firstly, self-enhancing an original image RawImagSmall (x, y) of a second image to obtain MultImag (x, y); self-enhancement is to divide the square of the gray value of each pixel point (x, y) in the original image by the average gray value of the image; the relationship is as follows:
MultImag(x,y)= RawImagSmall (x,y)* RawImagSmall (x,y)/mean(RawImagSmall (x,y))
here, mean (RawImagSmall (x, y)) is a grayscale mean of the image RawImagSmall (x, y).
Then, the enhanced image MultImag (x, y) is transformed from the RGB image to the HSV color space, resulting in an S-channel image SactImag (x, y).
Threshold segmentation: firstly, setting the detection sensitivity of a second camera, wherein the range of the detection sensitivity is [0,1 ]; then, a segmentation threshold is calculated according to the detection sensitivity, and the relationship between the segmentation threshold and the sensitivity is calculated as follows:
ThresholdSmall =（-SensitivitySmall）* 128 + 255
wherein SensitivitySmall is the camera detection sensitivity of the second camera, and threshold small is the segmentation threshold.
And finally, extracting a sucker printing region RegionSucker from the threshold segmentation image.
And finally, performing threshold segmentation on the S-channel image Sactimag (x, y) according to a segmentation threshold ThresholdSmall, and extracting a defect region RegionSucker.
Selecting characteristics: and (4) screening a RegionSuckerInSmall (x, y) region possibly corresponding to the sucker print from the defective region RegionSucker according to the characteristics of the area, the circularity and the like of the sucker print.
So far, the suction mark defect detection of the second camera is completed.
S4: calculating the contact ratio of the first defect region and the second defect region, and filtering out the first defect region with the contact ratio larger than a preset contact ratio threshold value;
firstly, restoring a RegionSuckerInSmall (x, y) region extracted from a second image according to the image transformation ratio of a first image and the second image to obtain a RegionSuckerSmallTrans (x, y) region; the reduction relationship is as follows:
RegionSuckerSmallTrans（x,y）= RegionSuckerInSmall（Sacle(x)*x, Sacle(y)*y）
wherein, sacle (x) and sacle (y) are the row scaling ratio and the column scaling ratio of the first camera and the second camera.
After the reduction, the contact ratio between the defective region RegionDefectInBig (x, y) and RegionSuckerSmallTrans (x, y) is calculated, and the contact ratio between the RegionDefectInBig (x, y) and RegionSuckerSmallTrans (x, y) is selected to be larger than the region RegionSuckerInBig (x, y) of the preset contact ratio interface parameter, wherein the region is a sucker printing region in the first image, and the contact ratio interface parameter range is 0 ~ 1, generally set to 0.7, and can be set according to specific conditions.
Finally, RegionSuckerInBig (x, y) in the RegionDefectInBig (x, y) region is filtered out, thereby reducing the over-detection.
In the embodiment, the defect filtering is performed in a mode of combining the first camera and the second camera, the contact ratio between the defect areas is used as a judgment index, the defect areas detected by the first camera are filtered through the defect areas detected by the second camera, the sucking disc printing areas are effectively screened out and filtered, the sucking disc printing is prevented from being mistakenly detected as the defect, and the over-detection rate is effectively reduced.
The embodiment also provides a system for reducing the panel defect overdetection rate, which comprises an acquisition unit, a correction unit, a calibration unit, a defect detection unit and a filtering unit, referring to fig. 2, wherein,
the acquisition unit is used for acquiring a first image of a display picture of a panel to be detected, which is shot by the first camera, and a second image of the same display picture, which is shot by the second camera; in this embodiment, the second camera is a color camera and has a resolution less than that of the first camera;
the correction unit is used for respectively carrying out distortion correction and perspective transformation on the first image and the second image; the distortion correction mainly aims at eliminating the influence of radial distortion of a lens; the main purpose of the perspective transformation is to correct the acquired oblique images.
The calibration unit is used for calibrating the first image and the second image acquired by the acquisition unit to obtain an image transformation ratio between the first image and the second image; the image transformation ratio comprises a row scaling ratio and a column scaling ratio; calculating a line scaling ratio according to the lengths of the horizontal calibration line in the first camera and the second camera; the column scaling ratio is calculated from the lengths of the vertical calibration lines in the first and second cameras.
The defect detection unit is used for carrying out defect detection on the first image to obtain a first defect area to be filtered; the second defect area is used for detecting the defects of the second image to obtain a second defect area to be filtered; in this embodiment, the defect detection unit includes a first detection module and a second detection module;
the first detection module is configured to perform median filtering and image enhancement on the first image, and may also adopt filtering manners such as mean filtering and gaussian filtering, which is not specifically limited in this embodiment;
then, calculating a segmentation threshold according to the detection sensitivity of the first camera, performing threshold segmentation on the first image after the image enhancement according to the segmentation threshold, and extracting a defect area from the first image;
and finally, screening out a first defect region which possibly corresponds to the suction cup print from the defect regions of the first image according to the characteristics of the area, the circularity and the like of the suction cup print.
The second detection module is used for carrying out self-enhancement on the second image, converting the enhanced second image into an HSV color space and extracting an S-channel image; the self-enhancement of the second image is specifically to divide the square of the gray value of each pixel point in the second image by the average gray value of the second image;
then, calculating a segmentation threshold according to the detection sensitivity of the second camera, performing threshold segmentation on the S-channel image according to the segmentation threshold, and extracting a defect area from the second image;
and finally, screening out a second defect region which possibly corresponds to the suction pad print from the defect region of the second image according to the characteristics of the area, the circularity and the like of the suction pad print.
The filtering unit is used for zooming the second defect area in rows and columns according to the image transformation ratio, calculating the contact ratio of the first defect area and the zoomed second defect area, wherein the first defect area with the contact ratio larger than a preset contact ratio interface parameter is a sucking disc printing area, and the sucking disc printing area is filtered, and the contact ratio interface parameter range of 0 ~ 1 is generally set to be 0.7 and can be set according to specific conditions.
The present embodiment also provides a terminal device, which includes at least one processor and at least one memory, where the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to execute the steps of the method for reducing the panel defect overdetection rate. The type of processor and memory are not particularly limited, for example: the processor may be a microprocessor, digital information processor, on-chip programmable logic system, or the like; the memory may be volatile memory, non-volatile memory, a combination thereof, or the like.
The present embodiment also provides a computer readable medium, which stores a computer program executable by a terminal device, and when the computer program runs on the terminal device, the computer program causes the terminal device to execute the steps of the above method for reducing the panel defect overdetection rate. Types of computer readable media include, but are not limited to, storage media such as SD cards, usb disks, fixed hard disks, removable hard disks, and the like.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for reducing the panel defect overdetection rate is characterized by comprising the following steps:
acquiring a first image of a display picture of a panel to be detected shot by a first camera and a second image of the display picture shot by a second camera; the second camera is a color camera;
extracting a first defect area to be filtered in the first image;
transforming the second image to an HSV color space, extracting an S-channel image and extracting a second defect area to be filtered from the S-channel image;
and calculating the coincidence degree of the first defect region and the second defect region correspondingly extracted from the first image and the second image with the same size, and filtering out the first defect region with the coincidence degree larger than a preset coincidence degree threshold value.
2. The method for reducing the panel defect overdetection rate of claim 1, further comprising:
calibrating the first image and the second image to obtain an image transformation ratio between the first image and the second image; scaling the second defective region according to the image transformation ratio to match the size of the first defective region.
3. The method for reducing the panel defect overdetection rate according to claim 1, wherein the extracting of the first defect region to be filtered in the first image specifically comprises:
filtering and enhancing the first image;
and calculating a segmentation threshold according to the detection sensitivity of the first camera, and performing threshold segmentation and feature selection on the enhanced first image according to the segmentation threshold to obtain a first defect region to be filtered.
4. The method for reducing the panel defect overdetection rate according to claim 1, wherein the extracting of the second defect region to be filtered from the S-channel image specifically comprises:
and calculating a segmentation threshold according to the detection sensitivity of the second camera, and performing threshold segmentation and feature selection on the S-channel image according to the segmentation threshold to obtain a second defect area to be filtered.
5. The method of reducing panel defect undetection rate of claim 1, wherein transforming the second image to HSV color space further comprises:
and self-enhancing the second image, and dividing the square of the gray value of each pixel point in the second image by the average gray value of the second image.
6. The method for reducing the panel defect overdetection rate according to claim 2, wherein before calibrating the first image and the second image, the method further comprises: and carrying out distortion correction and perspective transformation on the first image and the second image.
7. A system for reducing the rate of panel defect review, the system comprising:
the device comprises an acquisition unit, a display unit and a control unit, wherein the acquisition unit is used for acquiring a first image of a display picture of a panel to be detected, which is shot by a first camera, and a second image of the display picture, which is shot by a second camera;
the defect detection unit is used for extracting a first defect area to be filtered in the first image; the second image is transformed to an HSV color space, an S channel image is extracted, and a second defect area to be filtered is extracted from the S channel image;
and the filtering unit is used for calculating the coincidence degree of the first defect region and the second defect region correspondingly extracted from the first image and the second image with the same size, and filtering out the first defect region with the coincidence degree larger than a preset coincidence degree threshold value.
8. The system for reducing the panel defect overdetection rate as claimed in claim 7, further comprising a calibration unit;
the calibration unit is used for calibrating the first image and the second image to obtain the image transformation ratio between the first image and the second image;
the filtering unit scales the second defect region to match the size of the first defect region according to the image transformation ratio.
9. The system for reducing the panel defect overdetection rate according to claim 7 or 8, further comprising a correction unit; the correction unit is used for carrying out distortion correction and perspective transformation on the first image and the second image.
10. A terminal device, comprising at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to carry out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910965886.6A CN110458840B (en) | 2019-10-12 | 2019-10-12 | Method, system and terminal equipment for reducing panel defect over-detection rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910965886.6A CN110458840B (en) | 2019-10-12 | 2019-10-12 | Method, system and terminal equipment for reducing panel defect over-detection rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110458840A CN110458840A (en) | 2019-11-15 |
| CN110458840B true CN110458840B (en) | 2020-01-14 |
Family
ID=68492795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910965886.6A Active CN110458840B (en) | 2019-10-12 | 2019-10-12 | Method, system and terminal equipment for reducing panel defect over-detection rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110458840B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107561737A (en) * | 2017-08-21 | 2018-01-09 | 武汉精测电子技术股份有限公司 | A kind of method, apparatus and instrument of AOI system IPC parameter adjust automaticallies |
| CN108710655A (en) * | 2018-05-10 | 2018-10-26 | 武汉精测电子集团股份有限公司 | A kind of AOI based on database crosses missing inspection information analysis method and system |
| US10204408B2 (en) * | 2015-05-28 | 2019-02-12 | Jabil Inc. | System, apparatus and method for dispensed adhesive material inspection |
| CN109490311A (en) * | 2018-10-25 | 2019-03-19 | 武汉精立电子技术有限公司 | Backlight panel defect detecting system and method based on multi-angled shooting |
| CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107389689B (en) * | 2017-07-26 | 2020-05-22 | 武汉精测电子集团股份有限公司 | AOI management system and management method for defect detection |
-
2019
- 2019-10-12 CN CN201910965886.6A patent/CN110458840B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10204408B2 (en) * | 2015-05-28 | 2019-02-12 | Jabil Inc. | System, apparatus and method for dispensed adhesive material inspection |
| CN107561737A (en) * | 2017-08-21 | 2018-01-09 | 武汉精测电子技术股份有限公司 | A kind of method, apparatus and instrument of AOI system IPC parameter adjust automaticallies |
| CN108710655A (en) * | 2018-05-10 | 2018-10-26 | 武汉精测电子集团股份有限公司 | A kind of AOI based on database crosses missing inspection information analysis method and system |
| CN109490311A (en) * | 2018-10-25 | 2019-03-19 | 武汉精立电子技术有限公司 | Backlight panel defect detecting system and method based on multi-angled shooting |
| CN109856156A (en) * | 2019-01-22 | 2019-06-07 | 武汉精立电子技术有限公司 | A kind of display panel tiny flaw determination method and device based on AOI |
Non-Patent Citations (1)
| Title |
|---|
| 自动光学检测机边缘检测及非整数倍率检测优化;王旭 等;《电子世界》;20190731;第9-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110458840A (en) | 2019-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8391585B2 (en) | Defect detecting device, defect detecting method, image sensor device, image sensor module, defect detecting program, and computer-readable recording medium | |
| US9292915B2 (en) | Digital optical comparator | |
| JP4399494B2 (en) | Defect detection apparatus, defect detection method, image sensor device, and image sensor module | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN109872309B (en) | Detection system, method, device and computer readable storage medium | |
| CN1690678A (en) | Image analysis method, image analysis program and pixel evaluation system having the sames | |
| JP2005331929A (en) | Image analysis method, image analysis program, and pixel evaluation system therewith | |
| WO2017020829A1 (en) | Resolution testing method and resolution testing device | |
| CN112686920A (en) | Visual measurement method and system for geometric dimension parameters of circular part | |
| JP2005331929A5 (en) | ||
| CN108871185B (en) | Method, device and equipment for detecting parts and computer readable storage medium | |
| CN110648330B (en) | Defect detection method for camera glass | |
| CN115561247A (en) | Automatic visual inspection system for appearance of electronic component | |
| CN112801947A (en) | Visual detection method for dead pixel of LED display terminal | |
| CN113785181A (en) | OLED screen point defect judgment method and device, storage medium and electronic equipment | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN113781396A (en) | Screen defect detection method, device, equipment and storage medium | |
| KR20190023374A (en) | Method for testing display pannel | |
| CN114565558A (en) | CMOS chip surface defect detection method and system | |
| CN116563298B (en) | Cross line center sub-pixel detection method based on Gaussian fitting | |
| CN110458840B (en) | Method, system and terminal equipment for reducing panel defect over-detection rate | |
| JP2006155579A (en) | Image processing method and image processing apparatus | |
| CN104980718A (en) | Color correction devices and methods | |
| US20060126136A1 (en) | Image inspecting apparatus, image inspecting method, control program and computer-readable storage medium | |
| JP2009281759A (en) | Color filter defect inspection method, inspection apparatus, and color filter manufacturing method using it |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |